基于RBF神经网络的分布式光伏综合电价测算方法  

A Distributed Photovoltaic Comprehensive Electricity Price Calculation Method Based on RBF Neural Network

作　　者：王庆 WANG Qing(ShenzhenXinneng Electric Power Development and Design Institute Co.,Ltd.Guangdong Shenzhen 518052)

机构地区：[1]深圳新能电力开发设计院有限公司,广东深圳518052

出　　处：《长江信息通信》2024年第11期21-23,共3页Changjiang Information & Communications

摘　　要：常规的分布式光伏综合电价测算结构一般会采用目标式,测算的偏差较大,导致最终得出的功率因数降低,为此提出对基于RBF神经网络的分布式光伏综合电价测算方法的设计与分析。根据当前的测算目标,先进行周期电价数据归一化处理,采用多阶的方式,把控测算的偏差,确定RBF神经网络多阶测算结构。基于此,设计RBF神经网络分布式光伏综合电价测算模型,采用动态核验的方式来实现综合测算。测试结果表明:对比于传统改进长期增量成本法光伏综合电价测算方法、传统的需求响应光伏综合电价测算方法,此次设计的RBF神经网络光伏综合电价测算方法最终得出的功率因数较高,这说明该测试计算得出的用电效率高,电费相对较少,测算结果更加精准,具有实际的应用价值。The conventional structure for calculating the comprehensive electricity price of distributed photovoltaics generally adopts a target formula,which results in a large deviation in the calculation and leads to a decrease in the final power factor.Therefore,the paper proposes the design and analysis of a distributed photovoltaic comprehensive electricity price calculation method based on RBF neural network.Based on the current calculation target,normalize the periodic electricity price data first,adopt a multi-stage approach to control the deviation of the calculation,and determine the multi-stage calculation structure of the RBF neural network.Based on this,design an RBF neural network distributed photovoltaic comprehensive electricity price calculation model,and use dynamic verification to achieve comprehensive calculation.The test results show that compared with the traditional improved long-term incremental cost method for photovoltaic comprehensive electricity price calculation and the traditional demand response photovoltaic comprehensive electricity price calculation method,the RBF neural network photovoltaic comprehensive electricity price calculation method designed the time ultimately obtains a higher power factor.The indicates that the electricity efficiency calculated in the test is high,the electricity cost is relatively low,the calculation results are more accurate,and it has practical application value.

关 键 词：RBF神经网络 分布式处理 光伏设计 综合电价 电力预测 测算方法 

分 类 号：TM715[电气工程—电力系统及自动化]